Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    blouse

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (ARG
    -0.07
    >>)
    -0.07
    Pes
    -0.07
    	logging
    -0.07
    İŞ
    -0.07
    MLE
    -0.07
    argc
    -0.07
    >D
    -0.06
    ryptography
    -0.06
     restructuring
    -0.06
    POSITIVE LOGITS
    좨
    0.07
     Cowboys
    0.07
     dụng
    0.07
    自来水
    0.07
     bathrooms
    0.07
     occupies
    0.07
     squad
    0.07
     général
    0.07
    HE
    0.06
    �
    0.06
    Act Density 0.003%

    No Known Activations